CN112816483A - Group fog recognition early warning method and system based on fog value analysis and electronic equipment - Google Patents
Group fog recognition early warning method and system based on fog value analysis and electronic equipment Download PDFInfo
- Publication number
- CN112816483A CN112816483A CN202011643435.XA CN202011643435A CN112816483A CN 112816483 A CN112816483 A CN 112816483A CN 202011643435 A CN202011643435 A CN 202011643435A CN 112816483 A CN112816483 A CN 112816483A
- Authority
- CN
- China
- Prior art keywords
- fog
- value
- image
- sub
- values
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 title claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 20
- 239000003595 mist Substances 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 3
- 206010039203 Road traffic accident Diseases 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 230000036626 alertness Effects 0.000 abstract 1
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
- G01N2021/8578—Gaseous flow
Landscapes
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Emergency Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a group fog recognition early warning method, a group fog recognition early warning system and electronic equipment based on fog value analysis, wherein the group fog recognition early warning method comprises the following steps: acquiring a scene image of a target scene; performing matrix segmentation on a scene image to form a plurality of sub-image areas; carrying out matrix segmentation on the subimage areas by using unit image blocks, and calculating to obtain fog values of the subimage areas; sequentially acquiring fog values of all sub-image areas to form a fog value array FV; and calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values. The invention solves the problems that the prior art can not carry out intelligent, efficient, rapid and convenient monitoring, evaluation and early warning on the cluster fog, so that when the cluster fog appears on a road, the driver still has certain delay on the alertness of the cluster fog, can not carry out traffic safety precaution in time, and has traffic accident potential.
Description
Technical Field
The invention relates to the technical field of intelligent traffic safety, in particular to a group fog recognition early warning method and system based on fog value analysis and electronic equipment.
Background
In recent years, with the rapid development of the economy of China, the road transportation industry is also changing day by day. In China, road traffic has the characteristics of convenience, rapidness, mobility and flexibility, so that the road traffic has a leading position in various transportation modes.
Along with the continuous expansion trend of the scale of road traffic, the accident rate of the road traffic is also continuously improved, and the traffic safety gradually becomes the topic concerned and objected by people.
The fog is also called lump fog, which is affected by the microclimate environment of local regions, and in the local range of tens to hundreds of meters in the big fog, the fog with lower visibility appears. The fog cluster has the characteristics of strong regionality and high prediction difficulty, and can cause the sudden change of visibility on a highway, particularly on an expressway, instantly influence the sight of drivers, have great harm to the traffic safety of the expressway and easily cause major traffic accidents. Thus, the cloud is known as a "stealth killer" for road traffic safety.
At present traffic safety field, still can't carry out intelligent, high-efficient, rapid, convenient monitoring aassessment early warning to group fog at present, consequently, when group fog appears in the highway, the navigating mate still has certain delay nature to the vigilance of group fog, can't in time carry out traffic safety and prevent, has promoted the hidden danger that the traffic accident takes place.
Disclosure of Invention
The invention mainly aims to provide a group fog recognition early warning method, a group fog recognition early warning system and electronic equipment based on fog value analysis, and aims to solve the problems that in the prior art, the group fog cannot be intelligently, efficiently, quickly and conveniently monitored, evaluated and early warned, when the group fog appears on a road, the driver still has certain delay on the group fog, the traffic safety precaution cannot be carried out in time, and the potential hazard of traffic accidents exists.
In order to achieve the above object, according to an aspect of the present invention, there is provided a cloud identification warning method based on a fog value analysis, including: step S1, acquiring a scene image of a target scene; a step S2 of matrix-dividing the scene image in the width direction and the height direction of the scene image to form a plurality of sub-image areas (a); step S3, performing matrix division on the sub-image area (a) by using a plurality of unit image blocks (b), and calculating the fog value of the sub-image area (a) according to the dark channel value and the average brightness value of the unit image blocks (b) contained in the sub-image area (a); step S4, fog values of all the sub-image areas (a) are sequentially acquired to form a fog value array FV; and calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values.
Further, in step S4, when the average value of the fog value adjacent difference, meanDiff, is less than 10, when the average value of the fog value, meanAll, is greater than or equal to 80, it is determined that the target scene is a clear area, and when the average value of the fog value, meanAll, is less than 80, it is determined that the target scene is a cloud risk area; and under the condition that the fog value adjacent difference average value meanDiff is more than or equal to 10, judging that the target scene is a clear area or a cluster fog risk area according to the farthest visible distance of the movable object in the scene image.
Further, after the target scene is judged to be the cluster fog risk area, the cluster fog level of the target scene is analyzed and divided according to the threshold value of the average value mean of fog values; when the average fog value meanAll falls into [0, 30 ], judging that the cluster fog level of the target scene is severe; when the average fog value meanAll falls within [30, 50 ], judging that the cluster fog level of the target scene is secondary gravity; when the average fog value meanAll falls within [50, 70 ], judging that the cluster fog level of the target scene is moderate; when the fog value average meanAll falls within [70, 80 ], the cluster fog level of the target scene is determined to be light.
Further, in step S3, performing a difference calculation on a plurality of dark channel values of each unit image block (b) in each sub-image area (a) to obtain a middle dark channel array; carrying out differential calculation on a plurality of average brightness values of all unit image blocks (b) in each sub-image area (a) to obtain an average brightness array; and (3) calculating the arithmetic mean value of all data in the intermediate dark channel array and the average brightness array to obtain the fog value of the sub-image area (a).
Furthermore, the dark channel value of the unit image block (b) takes the minimum value of the RGB values of all the pixel points in the unit image block (b); the average luminance value of the unit image block (b) is calculated by the public indicator (1):
wherein, L (x, y) is the brightness value of the pixel point in the unit image block (b); n is the number of pixel points of the unit image block (b); δ is 0.0001, which is used to prevent the logarithm calculation result from approaching infinity.
Furthermore, the unit image block (b) comprises n multiplied by n pixel points, wherein n is more than or equal to 2 and less than or equal to 10.
Further, after step S2, the method further includes: step S21, scaling the sub-image area (a) to make the pixel of the sub-image area (a) larger than the pixel of the unit image block (b), and the sub-image area (a) contains m × m pixel points, where m is an integer multiple of n.
Further, in step S2, the height of the sub-image area (a) is 1/m of the height of the scene image, the width of the sub-image area (a) is 1/m of the width of the scene image, and 1 ≦ m ≦ 10.
According to another aspect of the present invention, there is provided a cloud recognition and early warning system, including: the image acquisition module is used for acquiring a scene image of a target scene; a feature calculation module for matrix-dividing the scene image in a width direction and a height direction of the scene image to form a plurality of sub-image regions (a); performing matrix division on the sub-image area (a) by using a plurality of unit image blocks (b), and calculating a fog value of the sub-image area (a) according to a dark channel value and an average brightness value of the unit image blocks (b) contained in the sub-image area (a); the analysis processing module is used for sequentially acquiring fog values of all the subimage areas (a) to form a fog value array FV; calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values; when the target scene is judged to be the cluster fog risk area, sending an early warning signal outwards; and the terminal early warning module is used for sending out a prompt alarm after receiving the early warning signal.
According to another aspect of the present invention, there is provided an electronic apparatus including: a processor and a memory; wherein, the processor is connected with the memory in a communication way; the processor is used for executing the group fog recognition early warning program stored in the memory so as to realize the group fog recognition early warning method.
By applying the technical scheme of the invention, the scene image of the target scene is subjected to the segmented fog value analysis by the image analysis processing technology, so that whether the target scene has a cluster fog risk or not can be reliably and accurately judged, and the risk early warning to a driver can be timely facilitated; the group fog recognition early warning method provided by the invention is simple and feasible, is convenient to apply, is beneficial to construction of a later defogging model, optimizes the transmissivity, realizes defogging of a scene image, provides a high-visibility image in a target scene for a driver, and improves the driving safety.
As shown in fig. 2 and 3, the scene image is matrix-divided, i.e., the scene image is matting, in the width direction W and the height direction H of the scene image to form a plurality of sub-image regions (a). When fog is in the target scene, the scene image is a foggy image, the fog distribution is not always uniform, and the brightness of the foggy image is not uniform, so that the scene image is processed in a subarea mode, the fog values of the sub-image areas (a) are obtained one by one, and the fog value array FV formed by combining the fog values of the sub-image areas (a) is calculated and analyzed in the later stage, so that the accuracy of judging the real-time scene state of the scene image is improved. Specifically, the average value meanAll of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values are calculated, and the target scene is rapidly judged to be a clear region or a cluster fog risk region according to the average value meanAll and the fog value array FV, and information is fed back.
In addition, in the scheme, a plurality of unit image blocks (b) are used for carrying out matrix division on each sub-image area (a), the unit image blocks (b) are used as basic analysis elements, and the fog value of the sub-image area (a) is obtained by calculation by utilizing the dark channel values and the average brightness values of all the unit image blocks (b) contained in each sub-image area (a); therefore, the fog value result obtained by combining the average brightness information and the dark channel information has good robustness.
Therefore, the group fog identification and early warning method can be used for carrying out intelligent, efficient, rapid and convenient monitoring, evaluation and early warning on the group fog in the target scene, when the target scene is judged to be the group fog risk area, the early warning can be effectively carried out, so that drivers can be ensured to take emergency measures such as braking, avoiding and the like in time, the road accident rate is reliably reduced, and the road traffic safety is greatly improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 illustrates a flow diagram of a cloud identification warning method based on fog value analysis according to an alternative embodiment of the present invention;
FIG. 2 illustrates a scene image of a target scene in accordance with an alternative embodiment of the present invention;
fig. 3 is a schematic diagram illustrating matrix segmentation of the scene image in fig. 2 by using the cloud identification early warning method based on the fog value analysis provided by the invention.
Wherein the figures include the following reference numerals:
a. a sub-image area; b. and (5) unit image blocks.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," "includes," "including," "has," "having," and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention provides a group fog recognition early warning method, a group fog recognition early warning system and electronic equipment based on fog value analysis, wherein the group fog recognition early warning system comprises an image acquisition module, a characteristic calculation module, an analysis processing module and a terminal early warning module, and the image acquisition module is used for acquiring a scene image of a target scene; the characteristic calculation module is used for carrying out matrix segmentation on the scene image along the width direction and the height direction of the scene image to form a plurality of sub-image areas (a); performing matrix division on the sub-image area (a) by using a plurality of unit image blocks (b), and calculating a fog value of the sub-image area (a) according to a dark channel value and an average brightness value of the unit image blocks (b) contained in the sub-image area (a); the analysis processing module is used for sequentially acquiring fog values of all the sub-image areas (a) to form a fog value array FV; calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values; when the target scene is judged to be the cluster fog risk area, sending an early warning signal outwards; the terminal early warning module is used for sending out a prompt alarm after receiving the early warning signal. The electronic device includes: a processor and a memory; wherein, the processor is connected with the memory in a communication way; the processor is used for executing the group fog recognition early-warning program stored in the memory so as to realize the group fog recognition early-warning method.
Fig. 1 is a flowchart of a cloud identification and early warning method based on a fog value analysis according to an alternative embodiment of the present invention. As shown in fig. 1, the method for identifying and warning the mist includes the following steps:
step S1, acquiring a scene image of a target scene;
a step S2 of matrix-dividing the scene image in the width direction and the height direction of the scene image to form a plurality of sub-image areas (a);
step S3, performing matrix division on the sub-image area (a) by using a plurality of unit image blocks (b), and calculating the fog value of the sub-image area (a) according to the dark channel value and the average brightness value of the unit image blocks (b) contained in the sub-image area (a);
step S4, fog values of all the sub-image areas (a) are sequentially acquired to form a fog value array FV; and calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values.
By carrying out segmentation type fog value analysis on the scene image of the target scene through the image analysis processing technology, whether the target scene has a cluster fog risk can be reliably and accurately judged, and early warning to a driver risk is facilitated in time; the group fog recognition early warning method provided by the invention is simple and feasible, is convenient to apply, is beneficial to construction of a later defogging model, optimizes the transmissivity, realizes defogging of a scene image, provides a high-visibility image in a target scene for a driver, and improves the driving safety.
As shown in fig. 2 and 3, the scene image is matrix-divided, i.e., the scene image is matting, in the width direction W and the height direction H of the scene image to form a plurality of sub-image regions (a). When fog is in the target scene, the scene image is a foggy image, the fog distribution is not always uniform, and the brightness of the foggy image is not uniform, so that the scene image is processed in a subarea mode, the fog values of the sub-image areas (a) are obtained one by one, and the fog value array FV formed by combining the fog values of the sub-image areas (a) is calculated and analyzed in the later stage, so that the accuracy of judging the real-time scene state of the scene image is improved.
In addition, in the scheme, a plurality of unit image blocks (b) are used for carrying out matrix division on each sub-image area (a), the unit image blocks (b) are used as basic analysis elements, and the fog value of the sub-image area (a) is obtained by calculation by utilizing the dark channel values and the average brightness values of all the unit image blocks (b) contained in each sub-image area (a); therefore, the fog value result obtained by combining the average brightness information and the dark channel information has good robustness.
Therefore, the group fog identification and early warning method can be used for carrying out intelligent, efficient, rapid and convenient monitoring, evaluation and early warning on the group fog in the target scene, when the target scene is judged to be the group fog risk area, the early warning can be effectively carried out, so that drivers can be ensured to take emergency measures such as braking, avoiding and the like in time, the road accident rate is reliably reduced, and the road traffic safety is greatly improved.
In this embodiment, it should be noted that in step S2, the height H of the sub-image area (a) is 1/m of the height H of the scene image, the width of the sub-image area (a) is 1/m of the height of the scene image, and 1 ≦ m ≦ 10. The arrangement is that when the scene image is subjected to image matting, the scene image is uniformly divided, so that the areas of the sub-image regions (a) are the same, any region of the scene image cannot be omitted, and the accuracy of the final real-time scene state judgment of the scene image is ensured. In the illustrated embodiment, as shown in fig. 3, the height H of the sub-image region (a) is 1/4 of the height H of the scene image, and the width W of the sub-image region (a) is 1/4 of the width W of the scene image. Of course, when the value of m is larger, the subsequent calculation complexity is larger, but the accuracy of the calculation result is higher. Preferably, m is 10.
Optionally, the unit image block (b) includes n × n pixel points, where n is greater than or equal to 2 and less than or equal to 10. In a preferred embodiment of the present invention, n-3. Thus, since the sub-image area (a) is divided into the plurality of unit image blocks (b) of 3 × 3, and the sub-image area (a) is divided into the plurality of unit image blocks (b) according to the present invention, when the sub-image area (a) is a fog image, the division of the sub-image area (a) needs to depend on the feature information of the fog image, that is, the dark channel information and the image luminance information of the unit image blocks (b).
The inventor of the invention discovers that in a non-sky area of a fog-free image, if the image is divided into a plurality of sub-blocks, the brightness of a color channel with certain pixel points in each sub-block is close to 0 through observation of a large number of fog-free image characteristics.
In foggy weather, due to additional atmospheric light, the brightness of an acquired image is often higher than that of a natural fogless image, and in a foggy scene image, the brightness is not uniform in different areas due to different fog concentrations; in a natural fog-free scene image, dark primary color areas are zero. The dark primary color value is calculated through the dark channel value, and under the fog condition, the value of the dark channel is increased due to the interference of fog.
In the invention, a plurality of dark channel values of each unit image block (b) in each sub-image area (a) are subjected to differential calculation to obtain a middle dark channel array; carrying out differential calculation on a plurality of average brightness values of all unit image blocks (b) in each sub-image area (a) to obtain an average brightness array; and (3) calculating the arithmetic mean value of all data in the intermediate dark channel array and the average brightness array to obtain the fog value of the sub-image area (a). Therefore, the fog value of the sub-image area (a) is obtained by integrating the information of the dark channel information and the image brightness information, namely after the difference calculation is carried out on the dark channel values and the average brightness values of the unit image blocks (b), the fog value of the sub-image area (a) is obtained by taking the arithmetic mean value, and the fog value directly reflects the fog concentration of the sub-image area (a).
In the preferred embodiment of the present invention, the dark channel value of the unit image block (b) is the minimum value among the RGB values of all the pixels in the unit image block (b); the average luminance value of the unit image block (b) is calculated by the public indicator (1):
wherein, L (x, y) is the brightness value of the pixel point in the unit image block (b); n is the number of pixel points of the unit image block (b); δ is 0.0001, which is used to prevent the logarithm calculation result from approaching infinity. Thus, the complexity of calculating the fog value of the sub-image area (a) is effectively reduced, and the accuracy of the calculation result can be ensured.
In order to improve the accuracy of judging whether a target scene is a clear area or a cluster fog risk area, the method uses the fog value average mean value meanAll and the fog value adjacent difference mean value meanDiff of all fog values in a fog value array FV consisting of the fog values of a plurality of sub-image areas (a) to quickly judge whether the target scene is the clear area or the cluster fog risk area, and feeds back information.
Specifically, under the condition that the average value of the fog value adjacent difference value meanDiff is less than 10, when the average value of the fog value meanAll is more than or equal to 80, the target scene is judged to be a clear area, and when the average value of the fog value meanAll is less than 80, the target scene is judged to be a cluster fog risk area; and under the condition that the fog value adjacent difference average value meanDiff is more than or equal to 10, judging that the target scene is a clear area or a cluster fog risk area according to the farthest visible distance of the movable object in the scene image.
Further, after the target scene is judged to be the cluster fog risk area, the cluster fog level of the target scene is analyzed and divided according to the threshold value of the average value mean of fog values; when the average fog value meanAll falls into [0, 30 ], judging that the cluster fog level of the target scene is severe; when the average fog value meanAll falls within [30, 50 ], judging that the cluster fog level of the target scene is secondary gravity; when the average fog value meanAll falls within [50, 70 ], judging that the cluster fog level of the target scene is moderate; when the fog value average meanAll falls within [70, 80 ], the cluster fog level of the target scene is determined to be light.
Optionally, in this embodiment, the cloud identification warning method may further include step S21, where the sub-image region (a) is scaled so that the pixel of the sub-image region (a) is larger than the pixel of the unit image block (b), and the sub-image region (a) includes m × m pixel points, where m is an integer multiple of n. Therefore, the adaptability of the sub-image area (a) and the unit image blocks (b) is improved, the sub-image area (a) can be perfectly covered by the unit image blocks (b), and the ordered calculation difficulty is greatly reduced.
Preferably, the sub-image area (a) may be scaled to 90 × 90 pixels, so that the sub-image area (a) is just divided into 900 unit image blocks (b) arranged in a matrix.
Preferably, the target scene in the invention is a driving road.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, network devices, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed client can be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A cluster fog recognition early warning method based on fog value analysis is characterized by comprising the following steps:
step S1, acquiring a scene image of a target scene;
a step S2 of matrix-dividing the scene image in a width direction and a height direction of the scene image to form a plurality of sub-image areas (a);
step S3, performing matrix segmentation on the sub-image area (a) by using a plurality of unit image blocks (b), and calculating the fog value of the sub-image area (a) according to the dark channel value and the average brightness value of the unit image blocks (b) contained in the sub-image area (a);
step S4, sequentially acquiring fog values of all the sub-image areas (a) to form a fog value array FV; and calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values.
2. The mist identification warning method according to claim 1,
in the step S4, in the above step,
in the case where the average value of the mist value adjacent differences, meanDiff, is < 10,
when the average fog value meanAll is more than or equal to 80, the target scene is judged to be a clear area,
when the average fog value meanAll is less than 80, judging that the target scene is a cluster fog risk area;
and under the condition that the fog value adjacent difference average mean meanDiff is more than or equal to 10, judging that the target scene is a clear area or a cluster fog risk area according to the farthest visible distance of the movable object in the scene image.
3. The mist identification warning method according to claim 2,
after the target scene is judged to be a cluster fog risk area, cluster fog grades of the target scene are analyzed and divided according to a threshold value of the average fog value mean al;
when the fog value average mean falls within [0, 30 ], judging that the cluster fog level of the target scene is severe;
when the fog value average mean falls within [30, 50 ], judging that the cluster fog level of the target scene is secondary gravity;
when the fog value average mean falls within [50, 70 ], determining that the cluster fog level of the target scene is moderate;
when the fog value average mean falls within [70, 80 ], determining that the cluster fog level of the target scene is light.
4. The mist identification warning method according to claim 1, wherein in the step S3,
carrying out differential calculation on a plurality of dark channel values of each unit image block (b) in each sub-image area (a) to obtain a middle dark channel array;
carrying out differential calculation on a plurality of average brightness values of all unit image blocks (b) in each sub-image area (a) to obtain an average brightness array;
and calculating the arithmetic mean value of all data in the middle dark channel array and the average brightness array to obtain the fog value of the sub-image area (a).
5. The mist identification and early warning method according to claim 4,
the dark channel value of the unit image block (b) is the minimum value of the RGB values of all the pixel points in the unit image block (b);
the average brightness value of the unit image block (b) is calculated by the public indicator (1):
wherein, L (x, y) is the brightness value of the pixel point in the unit image block (b); n is the number of pixel points of the unit image block (b); δ is 0.0001, which is used to prevent the logarithm calculation result from approaching infinity.
6. The fog cluster identification early warning method of claim 5, wherein the unit image block (b) comprises n × n pixel points, wherein n is greater than or equal to 2 and less than or equal to 10.
7. The mist identification and early warning method of claim 6, further comprising, after the step S2:
step S21, scaling the sub-image region (a) so that the pixels of the sub-image region (a) are larger than the pixels of the unit image block (b), and the sub-image region (a) includes m × m pixel points, where m is an integer multiple of n.
8. The cloud identification and early warning method of claim 1, wherein in step S2, the height of the sub-image area (a) is 1/m of the height of the scene image, the width of the sub-image area (a) is 1/m of the width of the scene image, and 1 ≦ m ≦ 10.
9. A group fog recognition early warning system, characterized by, includes:
the image acquisition module is used for acquiring a scene image of a target scene;
a feature calculation module for matrix-dividing the scene image in a width direction and a height direction of the scene image to form a plurality of sub-image regions (a); performing matrix segmentation on the sub-image area (a) by using a plurality of unit image blocks (b), and calculating a fog value of the sub-image area (a) according to a dark channel value and an average brightness value of the unit image blocks (b) contained in the sub-image area (a);
the analysis processing module is used for sequentially acquiring fog values of all the sub-image areas (a) to form a fog value array FV; calculating the average value meanAll of fog values of all fog values in the fog value array FV and the average value meanDiff of adjacent difference values of the fog values, and judging that the target scene is a clear area or a cluster fog risk area according to the average value meanAll and the average value meanDiff of the adjacent difference values of the fog values; when the target scene is judged to be the cluster fog risk area, sending an early warning signal outwards;
and the terminal early warning module is used for receiving the early warning signal and then sending out a prompt alarm.
10. An electronic device, comprising: a processor and a memory; wherein,
the processor is in communication connection with the memory;
the processor is used for executing the group fog identification early warning program stored in the memory to realize the group fog identification early warning method in any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643435.XA CN112816483A (en) | 2021-03-05 | 2021-03-05 | Group fog recognition early warning method and system based on fog value analysis and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643435.XA CN112816483A (en) | 2021-03-05 | 2021-03-05 | Group fog recognition early warning method and system based on fog value analysis and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112816483A true CN112816483A (en) | 2021-05-18 |
Family
ID=75858258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011643435.XA Pending CN112816483A (en) | 2021-03-05 | 2021-03-05 | Group fog recognition early warning method and system based on fog value analysis and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112816483A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313914A (en) * | 2021-05-28 | 2021-08-27 | 谢静芳 | Group fog monitoring method, device and system and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08315113A (en) * | 1995-05-18 | 1996-11-29 | Japan Radio Co Ltd | Method for detecting dust generation and smoke emission |
| CN107301623A (en) * | 2017-05-11 | 2017-10-27 | 北京理工大学珠海学院 | A kind of traffic image defogging method split based on dark and image and system |
| CN108681990A (en) * | 2018-04-04 | 2018-10-19 | 高明合 | A kind of real-time haze method for early warning and system |
| CN109886920A (en) * | 2019-01-16 | 2019-06-14 | 安徽谛听信息科技有限公司 | A kind of greasy weather stage division, greasy weather hierarchy system |
| CN111783732A (en) * | 2020-07-17 | 2020-10-16 | 上海商汤智能科技有限公司 | Group mist identification method and device, electronic equipment and storage medium |
| CN112200746A (en) * | 2020-10-16 | 2021-01-08 | 中南大学 | Defogging method and device for traffic scene image in foggy day |
-
2021
- 2021-03-05 CN CN202011643435.XA patent/CN112816483A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08315113A (en) * | 1995-05-18 | 1996-11-29 | Japan Radio Co Ltd | Method for detecting dust generation and smoke emission |
| CN107301623A (en) * | 2017-05-11 | 2017-10-27 | 北京理工大学珠海学院 | A kind of traffic image defogging method split based on dark and image and system |
| CN108681990A (en) * | 2018-04-04 | 2018-10-19 | 高明合 | A kind of real-time haze method for early warning and system |
| CN109886920A (en) * | 2019-01-16 | 2019-06-14 | 安徽谛听信息科技有限公司 | A kind of greasy weather stage division, greasy weather hierarchy system |
| CN111783732A (en) * | 2020-07-17 | 2020-10-16 | 上海商汤智能科技有限公司 | Group mist identification method and device, electronic equipment and storage medium |
| CN112200746A (en) * | 2020-10-16 | 2021-01-08 | 中南大学 | Defogging method and device for traffic scene image in foggy day |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313914A (en) * | 2021-05-28 | 2021-08-27 | 谢静芳 | Group fog monitoring method, device and system and storage medium |
| CN113313914B (en) * | 2021-05-28 | 2022-08-02 | 谢静芳 | Group fog monitoring method, device and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512623B (en) | Based on multisensor travelling in fog day vision enhancement and visibility early warning system and method | |
| CN111489588B (en) | Vehicle driving risk early warning method and device, equipment and storage medium | |
| CN107590470B (en) | Lane line detection method and device | |
| CN109448397B (en) | Group fog monitoring method based on big data | |
| KR20210080459A (en) | Lane detection method, apparatus, electronic device and readable storage medium | |
| KR20210078530A (en) | Lane property detection method, device, electronic device and readable storage medium | |
| CN113850123A (en) | Video-based road monitoring method and device, storage medium and monitoring system | |
| CN112215306A (en) | Target detection method based on fusion of monocular vision and millimeter wave radar | |
| CN106951898B (en) | Vehicle candidate area recommendation method and system and electronic equipment | |
| CN110837800A (en) | Port severe weather-oriented target detection and identification method | |
| WO2006115676A2 (en) | Video ghost detection by outline | |
| CN110610153A (en) | Lane recognition method and system for automatic driving | |
| CN111931726B (en) | Traffic light detection method, device, computer storage medium and road side equipment | |
| CN113887418A (en) | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium | |
| CN111144301A (en) | Road pavement defect quick early warning device based on degree of depth learning | |
| CN112818792A (en) | Lane line detection method, lane line detection device, electronic device, and computer storage medium | |
| US11748664B1 (en) | Systems for creating training data for determining vehicle following distance | |
| CN112837313A (en) | Image segmentation method for foreign matters in power transmission line | |
| CN112419745A (en) | Highway group fog early warning system based on degree of depth fusion network | |
| CN109191492A (en) | A kind of intelligent video black smoke vehicle detection method based on edge analysis | |
| CN112816483A (en) | Group fog recognition early warning method and system based on fog value analysis and electronic equipment | |
| CN111009136A (en) | Method, device and system for detecting vehicles with abnormal running speed on highway | |
| CN109330833B (en) | Intelligent sensing system and method for assisting visually impaired patients to safely go out | |
| CN116363100A (en) | Image quality evaluation method, device, equipment and storage medium | |
| CN115016453A (en) | Intelligent networking unmanned vehicle driving system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210518 |